Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description clearly states the permanent deletion and irreversibility, which is appropriate for a destructive tool. With no annotations provided, the description effectively conveys the behavioral impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences deliver key information with no waste. The irreversibility warning is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete tool with one parameter and no output schema, the description fully covers the action, effects, and implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents the 'template_id' parameter (100% coverage). The description adds value by explaining that deletion includes the version history, providing context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Supprime') and resource ('modèle'), and clearly distinguishes the tool from siblings as the only deletion tool among docx operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While the irreversibility warning implies caution, there is no explicit guidance on when to use this tool versus alternatives or prerequisites. Usage is implied but lacks explicit when-not-to-use context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavior fully. It states the tool downloads a file and returns a summary, but omits details like error handling, authentication requirements, or side effects. Adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no extraneous information. The primary action is front-loaded, and each sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter, no output schema, and no annotations, the description adequately covers core functionality and return value. Minor gaps (e.g., error conditions) exist but do not severely hinder completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (parameter template_id already well-described in schema). The tool description adds no additional meaning beyond what the schema provides, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Télécharge' and the resource 'fichier .docx d'un modèle déposé', and distinguishes from sibling docx_download_template_version by specifying it downloads the template file itself rather than a version. It also mentions the return format (size + truncated base64 preview).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like docx_download_template_version. The description does not provide context or exclusions, leaving the agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description discloses it returns a summary (size + truncated base64 preview) rather than full file, which is useful behavioral info. However, no annotations exist, and it could clarify if the actual file download is available or only the summary. Lacks details on auth or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, front-loaded with main action, second sentence adds return info. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description explains return value (summary). Sibling tools provide context. Missing error cases or prerequisites, but sufficient for core functionality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with basic descriptions. The tool description adds no extra meaning beyond 'ID du modèle' and 'ID numérique de la version archivée', which are already in schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Télécharge' and resource '.docx d'une version archivée d'un modèle', distinguishing it from siblings like docx_download_template (current version) and docx_restore_template_version (restores instead).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied (get archived version file), but no explicit when-to-use or when-not-to-use guidance, nor mention of alternatives like docx_download_template for current version.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It implies a read-only operation returning data, but does not explicitly state it is safe, idempotent, or authentication requirements. Adequate for basic understanding but lacks explicit behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is concise and front-loaded. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters, no output schema, and no annotations, the description is adequately complete. It covers what the tool does and what it returns. Could add more context about return structure or use cases, but sufficient for simple stats retrieval.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so schema coverage is 100%. Description does not need to add parameter details. Baseline 4 for zero parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns plan, quota (limit/used/remaining), and usage statistics for the DocX API key. It uses specific terms that distinguish it from sibling tools which focus on template and signature operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not provide context or conditions for invocation, such as checking usage before making API calls.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description correctly notes the client-side filtering behavior and scoping to the API key. However, it does not disclose authentication requirements, rate limits, or whether the list is paginated. This is adequate for a simple listing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main action, and contains no unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, and the description does not explain what the return value looks like (e.g., list of template names, metadata). For a listing tool, this missing information is a significant gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage for the single 'name' parameter. The description adds value by explaining that the filter is applied client-side and uses a 'contains' logic, which is beyond the schema's description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists Word templates for the API key, with an optional client-side name filter. This distinguishes it from sibling tools like docx_delete_template or docx_upload_template.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the optional filter and its client-side application, but lacks guidance on when to use this tool versus alternatives (e.g., docx_list_template_versions or docx_get_usage_stats). No explicit when-not or alternatives are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. It does not mention whether the operation is read-only, requires any permissions, or what happens if the template_id is invalid. It only describes the basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and front-loaded. However, it is slightly too brief and could benefit from a mention of the output format or usage hints without significant added length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple structure (one parameter, no output schema), the description is minimally adequate. It does not describe the return value (e.g., list of version metadata), which would help the agent understand what to expect. Annotations are absent, so more context would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the parameter has a clear description). The tool description adds no additional semantic value beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (list) and resource (versions d'un modèle), and specifies 'archived versions', which distinguishes from other version operations. However, it does not explicitly differentiate from sibling tools like docx_download_template_version, but the purpose is distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as docx_restore_template_version or docx_download_template_version. The description only states what it does without context for optimal use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses generation of documents and return of a summary, but does not detail constraints like template requirements, error handling, or output summary content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states the main action, second states the return value. No fluff, front-loaded, efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given good schema coverage and no output schema, the description is complete enough for basic understanding. It explains input and output but could mention template placeholders or error handling for full completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are already well-documented. The description adds context (document types) but no significant new semantic information beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a document (PDF or DOCX) from a template and JSON data, and returns a summary. It specifies the types of documents (quotes, contracts, certificates) and differentiates from sibling tools like docx_render_facturx and sign_ tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you need to generate a document from a template) but does not explicitly state when not to use it or mention alternative tools. It is clear but lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description partially compensates by stating the output format (PDF/A-3) and return summary. However, it lacks disclosure on error handling, idempotency, or template requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no waste. The purpose is front-loaded, and the return value is clearly mentioned. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters with full schema coverage and no output schema, the description explains the input and output sufficiently. It could be improved by mentioning error scenarios, but overall it covers the essential context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by providing an example JSON structure for the json_data parameter, which clarifies the expected format beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates Factur-X electronic invoices from a template and JSON data, distinguishing it from sibling tools like docx_render_document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for Factur-X invoices but does not explicitly guide when to use this tool over siblings like docx_render_document, nor does it provide exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the key behavioral trait that the current version is archived before overwriting. No annotations exist, so the description provides necessary transparency, but it lacks details on permissions, reversibility, or error states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main action. No redundant information. Every word serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema, the description covers core functionality and a side effect. However, it does not mention prerequisites, error handling, or how to retrieve the version_id. Slightly incomplete for a restoration action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning beyond what is in the schema, such as how to obtain the version_id (e.g., from docx_list_template_versions). Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: restoring an archived version as the active template version. It also mentions that the current version is archived before overwriting, which distinguishes it from sibling tools like docx_list_template_versions or docx_download_template_version.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., template must exist, version must be archived) or when not to use it. Sibling tools like docx_list_template_versions are implied but not explicitly referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses that the old version is archived and rollback is possible, adding valuable behavioral context. However, it does not mention any prerequisites or potential side effects beyond the archive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main action, no extraneous words. Each sentence contributes purpose and behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given sibling tools for create, list, restore, etc., the description covers the update operation with archiving detail. No output schema, but description need not explain return values. Could mention that the template must already exist.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds no additional meaning for parameters beyond what's in the schema (template_id, template_base64, template_name). The mention of archiving is not parameter-specific.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool replaces an existing template with a new .docx version, using 'remplace' (replace) and 'modèle existant'. This verb+resource distinction sets it apart from siblings like docx_upload_template (create new) and docx_restore_template_version (revert).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies when to use: to update a template. It lacks explicit exclusions or alternatives, but the context of sibling tools provides some differentiation. Missing a note like 'for uploading a new template, use docx_upload_template'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the full burden. It discloses that the file is base64 encoded and that the tool returns ID and detected tags. However, it omits behavioral aspects like whether existing templates with the same name get overwritten, any size limits, required permissions, or the format of output (e.g., response structure).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, with two efficient sentences. The first sentence front-loads the core purpose, and the second adds critical information about return value and encoding. No excess words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description provides essential information but lacks details on behavior like duplicate handling, file size constraints, or authorization. For a tool that performs a write operation, more context would be beneficial for successful invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already describes both parameters. The description adds minimal value beyond confirming that template_base64 is base64-encoded content, which aligns with the schema description. No additional semantics are provided for template_name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Dépose' (uploads) and the resource 'modèle Word (.docx)', and it distinguishes from sibling tools like docx_update_template by implying this is for creating/uploading a new template. It also mentions the return value of ID and detected tags, which further clarifies the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly guide when to use this tool versus alternatives such as docx_update_template or docx_list_templates. It implicitly suggests using it for initial template upload, but lacks explicit context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool mutates state (cancels) and fails if the document is already signed. This is sufficient for a simple cancel action, though additional details (e.g., whether cancellation triggers notifications) are absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main action and then the constraint. Every word is necessary and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter, no output schema, and no annotations, the description is complete: it states the primary function and a critical constraint. No additional information is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema coverage is 100% (one parameter documented). The description adds no extra meaning beyond the schema's description of 'document_id'. The baseline of 3 is appropriate as the schema already provides the necessary semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool cancels an ongoing signature request, using a specific verb ('Annule') and the resource ('une demande de signature'). It effectively distinguishes from siblings like sign_send_for_signature and sign_get_document_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a key condition: 'Impossible si le document est déjà signé', indicating when the tool cannot be used. It implies usage when a cancellation of an in-progress request is needed, though it does not explicitly state when to use it or mention alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full responsibility. It discloses that the tool analyzes the PDF and returns detected signature locations, implying a read-only operation, but does not explicitly state non-destructive behavior, error cases, or what happens if no tags are found. Basic transparency, but could be more thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two short sentences that efficiently convey the tool's purpose, input, and context. No redundant or filler words, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter and no output schema, the description covers the input but does not specify the return format (e.g., list of coordinates, bounding boxes) or error behavior. It hints at returning locations but lacks structural details. Adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter pdf_base64, which already describes its base64 encoding. The description repeats this information without adding new semantics. According to the calibration, baseline 3 is appropriate when schema coverage is high and description adds no extra meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states that the tool analyzes a PDF and returns detected signature locations marked with [[...]], specifying the verb 'analyse' and 'retourne' along with the resource 'PDF'. It also distinguishes from sibling tools by indicating it is used before sending for signature, and there are no similar detection tools among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'avant de l'envoyer à la signature' provides clear contextual guidance that this tool should be used before invoking sign_send_for_signature. While it does not explicitly list when not to use or alternative tools, the implicit usage context is strong enough for an agent to understand the workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It explains the nature of the signed PDF (PAdES, integrated certificate) and describes the response summary (title, size, truncated base64 preview). It does not cover authentication or potential errors, but provides solid behavioral insight.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is two short sentences in French, front-loaded with the core function and additional details. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one parameter, no output schema, and no annotations, the description covers the main aspects: what is retrieved, when available, and response content. Missing error handling details but sufficient for a simple download tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter (document_id) with 100% schema description coverage. The tool description does not add extra meaning beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states that the tool retrieves the final signed PDF (PAdES qualified signature with integrated proof certificate). It distinguishes from other sign tools like sign_get_audit_certificate or sign_validate_signature by focusing on downloading the signed document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description specifies that the document is available only after completion ('Disponible une fois le document complété'), providing clear context for when to use. It does not explicitly mention when not to use or alternatives, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Describes output contents (who, IP, time, hash) but lacks behavioral details like read-only nature, authentication, or rate limits. Adequate but not thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence efficiently conveys purpose and output details. Front-loaded with main verb. Could be slightly more structured but no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple schema and no output schema, description adequately explains result contents. However, missing prerequisite (e.g., document must be signed) and behavioral context. Not incomplete but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single required parameter document_id is described in schema. Description adds no extra parameter-level meaning but provides context on what the function returns. Schema coverage 100%, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'récupère' and resource 'certificat de preuve juridique complet' explicitly state the tool's action. Distinct from sibling tools like sign_download_signed_document, which downloads the signed file, not the certificate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., sign_validate_signature, sign_get_document_status). No prerequisites or exclusions stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It indicates a read-only operation by using 'consulte' and lists possible status outcomes. However, it does not specify the return format or any side effects, though none are expected for a status query.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is efficient and front-loaded with the tool's purpose. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple status tool with one parameter and no output schema, the description covers the purpose and status examples. It does not specify the structure of the response (e.g., returns a string or object), but the status list provides partial completeness. Almost adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes the single parameter 'document_id' as 'ID du document de signature.' The description adds no additional meaning beyond that, so baseline 3 applies given 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool consults the progress status of a signature request, listing examples of statuses (pending, signed, rejected). It distinguishes itself from sibling tools like sign_cancel_document (cancels) and sign_send_for_signature (sends request).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for checking status but lacks explicit guidance on when to use versus alternatives like sign_download_signed_document (after signing) or sign_validate_signature (validate a signature). No when/not-to-use conditions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must cover behavioral traits. It discloses the action (send PDF, create request, send email) but omits details like return values, side effects, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the core action without any extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is provided, and the description does not explain what the tool returns (e.g., a request ID), leaving the agent uncertain about the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description only reiterates that the PDF is base64 encoded, adding no additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sends a PDF for electronic signature, creates the request, and sends an invitation email, distinguishing it from other sign-related sibling tools like cancellation or status checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for initiating signature requests but lacks explicit guidance on when to use this tool versus alternatives like sign_detect_fields or sign_cancel_document.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states the action of sending an OTP but omits behavioral details such as side effects (SMS sent), prerequisites (e.g., document must exist), rate limits, error conditions, or whether it returns a confirmation. This lack of transparency is significant for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the core functionality. No redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description covers the basic purpose but lacks details on error handling, prerequisites, and what happens upon success/failure. For a sensitive SMS-sending tool, more information would be expected to ensure safe and correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameter descriptions are already present. The description adds contextual purpose ('to the signer for identity verification') but does not enhance the meaning of individual parameters beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it sends an OTP via SMS to the signer for identity verification before signing. The verb 'envoie' and specific resource 'code OTP par SMS' make the purpose unambiguous and distinguishable from sibling tools like sign_send_for_signature and sign_verify_otp.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context ('avant la signature'), indicating this tool is used before the signature step. However, it does not explicitly contrast with alternatives or state when not to use it, leaving partial clarity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully explain behavior. It discloses cryptographic verification but omits side effects (e.g., whether it modifies state), return type, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with verb, concise. Could be slightly more structured but efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a single-parameter tool with no output schema, but missing return type, error conditions, and usage context. The description is minimal but covers the core action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter (document_id) with full schema coverage. The description adds no additional meaning beyond what the schema already provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool cryptographically verifies the integrity and validity of a PAdES signature, which is a specific verb and resource. It distinguishes from sibling tools like sign_get_document_status or sign_download_signed_document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., document must be signed) or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It mentions success outcome but omits what happens on incorrect code (error/retry/lockout), and does not state side effects like invalidating the OTP.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the main action. It is efficient but lacks structure and important failure details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool is part of a signing flow, the description does not mention that it should be used after receiving an OTP or that the code has limited validity. No output schema is provided, but the URL return is mentioned.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the schema already describes all parameters. The description adds no additional meaning or context beyond what is in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (validate OTP code) and the outcome (returns signature URL if correct). It distinguishes from sibling tools like sign_send_otp which sends the code.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives, nor mention prerequisites like having sent an OTP first. Usage is implied but not clarified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.